Boosting Search Engines with Interactive Agents
This addresses the problem of enhancing information retrieval efficiency and interpretability for users of search engines, representing an incremental advancement by combining existing techniques in a novel way.
The paper tackles the problem of improving search engines by developing interactive agents that learn meta-strategies for iterative query refinement, achieving retrieval and answer quality performance comparable to recent neural methods using only traditional BM25 ranking and interpretable actions.
This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch. Our search agents obtain retrieval and answer quality performance comparable to recent neural methods, using only a traditional term-based BM25 ranking function and interpretable discrete reranking and filtering actions.